Design of a Visual Welding Defect Inspection Robot on The Outer Piping Line System based on The CNN Algorithm

Authors

Noorman Rinanto
Automation Engineering Study Program, Politeknik Perkapalan Negeri Surabaya
Ari Shinta
Automation Engineering Study Program, Politeknik Perkapalan Negeri Surabaya
Ryan Yudha Adhitya
Automation Engineering Study Program, Politeknik Perkapalan Negeri Surabaya
Mahmoud Elsisi
Electrical Engineering Department, National Kaohsiung University of Science and Technology, Kaohsiung, Taiwan
DOI: https://doi.org/10.52549/ijeei.v14i2.7641
Download PDF
Published: 19-04-2026 • Issue: Vol. 14 No. 2: June 2026 • Section: Regular paper

Abstract

The investigation focuses on using deep learning techniques to design a testing camera system and identify welding-related issues in outer pipes. The system uses an RGB camera, an ESP32 microcontroller, a DC motor with a rotary encoder, an LED strip, and a small computer that has a graphical user interface. This prototype was made to help with automating the inspection of carbon steel pipe welding, focusing on identifying and grouping different types of defects like porosity, undercut, and too much reinforcement. The results show that the system works in real time, achieving an average of 10.35 frames per second, taking 0.21 seconds to detect something, and having a confidence level of 97.13%. The built-in GUI shows the original image, the edge detection results, and the cropped ROI area, along with motor control and an LED strip. Mechanically, the prototype demonstrates sufficient stability for laboratory research; however, for industrial-scale research purposes, adjustments to materials and dimensions are required. This further develops an automated inspection system based on digital image processing and is designed to be safe, efficient, and compliant with safety standards.
Keywords: Welding Flaw Detection; Deep Learning; Pipeline Inspection; Automated Visual Inspection

References

T. Yin, J. Wang, H. Zhao, L. Zhou, Z. Xue, and H. Wang, “Research on Filling Strategy of Pipeline Multi-Layer Welding for Compound Narrow Gap Groove,†Materials, vol. 15, no. 17, p. 5967, 2022.

S. K. Sharma and S. Maheshwari, “A review on welding of high strength oil and gas pipeline steels,†J. Nat. Gas Sci. Eng., vol. 38, pp. 203–217, 2017.

G. Molnar, “Economics of gas transportation by pipeline and LNG,†in The Palgrave Handbook of International Energy Economics, M. Hafner and G. Luciani, Eds. Cham: Springer International Publishing, 2022, pp. 23–57.

J. B. Geng, Q. Ji, and Y. Fan, “A dynamic analysis on global natural gas trade network,†Appl. Energy, vol. 132, pp. 23–33, 2014.

V. Arora and Y. Cai, “US natural gas exports and their global impacts,†Appl. Energy, vol. 120, pp. 95–103, 2014.

M. P. Singh, D. K. Shukla, R. Kumar, and K. S. Arora, “The structural integrity of high-strength welded pipeline steels: A review,†International Journal of Structural Integrity, vol. 12, no. 3, pp. 470–496, 2021.

W. Hou, X. Zhang, J. Gao, et al., “Review on Computer Aided Weld Defect Detection from Radiography Images,†Appl. Sci., vol. 10, no. 5, p. 1878, 2020.

D. Palma-Ramírez, B. D. Ross-Veitía, P. Font-Ariosa, A. Espinel-Hernandez, A. Sanchez-Roca, H. Carvajal-Fals, J. R. Nuñez-Alvarez, and H. Hernandez-Herrera, “Deep convolutional neural network for weld defect classification in radiographic images,†Heliyon, vol. 10, no. 9, Art. no. e30590, 2024, doi: 10.1016/j.heliyon.2024.e30590.

H. Zhu, W. Ge, and Z. Liu, “Deep Learning-Based Classification of Weld Surface Defects,†Applied Sciences, vol. 9, no. 16, Art. no. 3312, 2019, doi: 10.3390/app9163312.

G. A. Elhendawy and Y. El-Taybany, “Machine Vision-Assisted Welding Defect Detection System with Convolutional Neural Networks,†Int. J. Precis. Eng. Manuf., pp. 1–10, 2025, doi: 10.1007/s12541-025-01281-y.

A. Spruck, J. Seiler, M. Roll, T. Dudziak, J. Eckstein, and A. Kaup, “Quality assurance of weld seams using laser triangulation imaging and deep neural networks,†in 2020 IEEE International Workshop on Metrology for Industry 4.0 & IoT, June 2020, pp. 407–412.

T. Tyystjarvi, I. Virkkunen, P. Fridolf, A. Rosell, and Z. Barsoum, “Automated defect detection in digital radiography of aerospace welds using deep learning,†Welding in the World, vol. 66, no. 4, pp. 643–671, 2022.

Y. Du, M. Liu, J. Wang, X. Liu, K. Wang, Z. Liu, Q. Dong, J. Yao, D. Lu, and Y. Su, “A wall climbing robot based on machine vision for automatic welding seam inspection,†Ocean Engineering, vol. 310, p. 118825, 2024.

M. Zhao, X. Liu, K. Wang, Z. Liu, Q. Dong, P. Wang, and Y. Su, “Welding seam tracking and inspection robot based on improved YOLOv8s-Seg model,†Sensors, vol. 24, no. 14, p. 4690, 2024.

P. Zhang, J. Wang, F. Zhang, P. Xu, L. Li, and B. Li, “Design and analysis of welding inspection robot,†Scientific Reports, vol. 12, no. 1, p. 22651, 2022.

J. Li, B. Li, L. Dong, X. Wang, and M. Tian, “Weld seam identification and tracking of inspection robot based on deep learning network,†Drones, vol. 6, no. 8, p. 216, 2022.

R. S. Elankavi, D. Dinakaran, A. S. A. Doss, R. M. K. Chetty, and M. M. Ramya, “Design and motion planning of a wheeled type pipeline inspection robot,†Journal of Robotics and Control (JRC), vol. 3, no. 4, pp. 415–430, 2022.

C. Xu, W. Jiang, H. Ma, Y. Liu, H. Men, X. Xu, and Z. Li, “A review: research and application of pipeline robots in the oil and gas industry,†Journal of Pipeline Science and Engineering, p. 100356, 2025.

S. Ren, K. He, R. Girshick, and J. Sun, “Faster R-CNN: Towards real-time object detection with region proposal networks,†IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137–1149, 2016.

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,†in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 779–788.

A. Niraula, H. Remes, and A. Nussbaumer, “Strain-based analysis on the influence of local undercut geometry on fatigue crack initiation life,†International Journal of Fatigue, vol. 186, p. 108392, 2024.

J. Chen, Y. Zhang, C. Wu, and G. K. Padhy, “Suppression of undercut defects in high-speed GMAW through a compound magnetic field,†J. Mater. Process. Technol., 2019, doi: 10.1016/j.jmatprotec.2019.116288.

KOBE STEEL, LTD., Weld Imperfections and Preventive Measures, Kobe Steel, Tokyo, Japan, 2015. [online] Available: https://www.kobelco-welding.jp/images/education-center/pdf/Defect_5Ed.pdf (accessed August 14, 2025).

American Welding Society, Structural Welding Code — Steel, AWS D1.1/D1.1M:2020, Miami, FL: American Welding Society, 2020. [online] Available: https://pubs.aws.org/Download_PDFS/D1_1_D1_1M_2020_index_PV.pdf (accessed September 16, 2025).

S. Shin and S. Rhee, “Porosity Characteristics and Effect on Tensile Shear Strength of High-Strength Galvanized Steel Sheets after the Gas Metal Arc Welding Process,†Metals, vol. 8, no. 12, art. 1077, Dec. 2018, doi: 10.3390/met8121077.

American Welding Society, A3.0M/A3.0 — Standard Welding Terms and Definitions, Miami, FL: American Welding Society, 2010. [online] Available: https://dl.gasplus.ir/standard-ha/Standard-AWS/AWS%20A3.0%202020.pdf (accessed October 2, 2025).

R. Reveles-Martínez, H. Gamboa-Rosales, E. Sanchez-Femat, J. Saldívar-Perez, T. Ibarra-Pérez, L. C. Reveles-Gómez, O. A. Guirette-Barbosa, J. I. Galvan-Tejada, C. E. Galván-Tejada, H. Luna-García, and J. M. Celaya-Padilla, “Benchmarking YOLOv8 to YOLOv11 Architectures for Real-Time Traffic Sign Recognition in Embedded 1:10 Scale Autonomous Vehicle,†Technologies, vol. 13, no. 11, p. 531, 2025.

How to Cite

[1]
N. Rinanto, A. Shinta, R. Y. Adhitya, and M. Elsisi, “Design of a Visual Welding Defect Inspection Robot on The Outer Piping Line System based on The CNN Algorithm”, IJEEI, vol. 14, no. 2, pp. 387–403, Apr. 2026, doi: 10.52549/ijeei.v14i2.7641.